© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128660
    Prev
    Next
    INDEX
    Explanations

    most followed by a descriptor

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is highly activated by the word “most,” i.e. it detects the quantifier “most.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     –
    -2.08
    -
    -1.88
     the
    -1.78
    ↵↵
    -1.73
     '
    -1.63
     praktische
    -1.63
     $-$
    -1.63
     lauded
    -1.62
     spearheaded
    -1.57
    </strong>
    -1.56
    POSITIVE LOGITS
     veta
    2.16
     dekoratif
    1.95
     mulus
    1.94
     mutiara
    1.94
    Because
    1.80
    Spesifikasi
    1.78
    Shortly
    1.77
    ंटर
    1.77
    !!!!!
    1.77
     cerdas
    1.76
    Activations Density 0.024%

    No Known Activations